CoSToM:Causal-oriented Steering for Intrinsic Theory-of-Mind Alignment in Large Language Models

• URL: http://arxiv.org/abs/2604.10031v1
• Date: Sat, 11 Apr 2026 05:04:37 GMT
• Title: CoSToM:Causal-oriented Steering for Intrinsic Theory-of-Mind Alignment in Large Language Models
• Abstract summary: Theory of Mind (ToM) is the ability to attribute mental states to others.<n>LLMs demonstrate promising performance on standard ToM benchmarks.<n>LLMs often fail to generalize to complex task-specific scenarios.
• Score: 23.229692182223157
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Theory of Mind (ToM), the ability to attribute mental states to others, is a hallmark of social intelligence. While large language models (LLMs) demonstrate promising performance on standard ToM benchmarks, we observe that they often fail to generalize to complex task-specific scenarios, relying heavily on prompt scaffolding to mimic reasoning. The critical misalignment between the internal knowledge and external behavior raises a fundamental question: Do LLMs truly possess intrinsic cognition, and can they externalize this internal knowledge into stable, high-quality behaviors? To answer this, we introduce CoSToM (Causal-oriented Steering for ToM alignment), a framework that transitions from mechanistic interpretation to active intervention. First, we employ causal tracing to map the internal distribution of ToM features, empirically uncovering the internal layers' characteristics in encoding fundamental ToM semantics. Building on this insight, we implement a lightweight alignment framework via targeted activation steering within these ToM-critical layers. Experiments demonstrate that CoSToM significantly enhances human-like social reasoning capabilities and downstream dialogue quality.

Related papers

• Beyond Sally-Anne: Evaluating Theory of Mind in LLMs using Epistemic Schelling Points [0.8703469130213444]
  We introduce the Epistemic Asymmetry Schelling Task (EAST), a two-player dialogue game designed to benchmark robust ToM abilities.<n>We evaluate whether models can robustly apply ToM to achieve coordination.<n>Our results reveal a significant capability gap in functional social reasoning.
  arXiv  Detail & Related papers  (2026-07-13T10:27:22Z)
• From Knowing to Acting: Benchmarking Self-Awareness Capability of LLM Agents [69.07911499189129]
  We introduce KAPRO, a framework that evaluates cognitive-behavioral alignment by decoupling an agent's metacognitive judgment (Knowing) from its spontaneous execution (Acting)<n>Experiments show that self-awareness capability is strongly correlated with task success but degrades sharply in internal-capability settings.<n> proprietary and reasoning-oriented models demonstrate more reliable cognitive gating.
  arXiv  Detail & Related papers  (2026-06-09T17:17:08Z)
• From Holistic Evaluation to Structured Criteria: Rubrics Across the Evolving LLM Landscape [79.30826980815927]
  rubrics are explicit criteria sets that transform complex quality judgments into structured and actionable standards.<n>We systematically organize existing rubric designs, examine their construction and optimization, and analyze their role across evaluation and training.
  arXiv  Detail & Related papers  (2026-06-07T13:34:55Z)
• Decomposing and Steering Functional Metacognition in Large Language Models [7.62618887128252]
  We show that large language models maintain a decomposable space of functional metacognitive states.<n>We show that these states are linearly decodable from internal activations and exhibit distinct layer-wise profiles.<n>Our findings suggest that benchmark performance reflects not only task competence but also the activation of specific functional metacognitive states.
  arXiv  Detail & Related papers  (2026-05-09T13:22:47Z)
• MirrorBench: Evaluating Self-centric Intelligence in MLLMs by Introducing a Mirror [68.92922229518848]
  We introduce MirrorBench, a simulation-based benchmark inspired by the classical Mirror Self-Recognition (MSR) test in psychology.<n>MirrorBench extends this paradigm to embodied MLLMs through a tiered framework of progressively challenging tasks.<n>Our study bridges psychological paradigms and embodied intelligence, offering a principled framework for evaluating the emergence of general intelligence in large models.
  arXiv  Detail & Related papers  (2026-04-16T08:45:34Z)
• Beyond Words: Evaluating and Bridging Epistemic Divergence in User-Agent Interaction via Theory of Mind [8.740788873949471]
  Large Language Models (LLMs) have developed rapidly and are widely applied to both general-purpose and professional tasks.<n>They still struggle to comprehend and respond to the true user needs when intentions and instructions are imprecisely conveyed.
  arXiv  Detail & Related papers  (2026-02-14T16:01:59Z)
• Investigating The Functional Roles of Attention Heads in Vision Language Models: Evidence for Reasoning Modules [76.21320451720764]
  We introduce CogVision, a dataset that decomposes complex multimodal questions into step-by-step subquestions.<n>Using a probing-based methodology, we identify attention heads that specialize in these functions and characterize them as functional heads.<n>Our analysis reveals that these functional heads are universally sparse, vary in number and distribution across functions, and mediate interactions and hierarchical organization.
  arXiv  Detail & Related papers  (2025-12-11T05:42:53Z)
• The Unified Cognitive Consciousness Theory for Language Models: Anchoring Semantics, Thresholds of Activation, and Emergent Reasoning [2.0800882594868293]
  Unified Cognitive Consciousness Theory (UCCT) casts them as vast unconscious pattern repositories.<n>UCCT formalizes this process as Bayesian competition between statistical priors learned in pre-training and context-driven target patterns.<n>We ground the theory in three principles: threshold crossing, modality, and density-distance predictive power.
  arXiv  Detail & Related papers  (2025-06-02T18:12:43Z)
• Scaling and Beyond: Advancing Spatial Reasoning in MLLMs Requires New Recipes [84.1059652774853]
  Multimodal Large Language Models (MLLMs) have demonstrated impressive performance in general vision-language tasks.<n>Recent studies have exposed critical limitations in their spatial reasoning capabilities.<n>This deficiency in spatial reasoning significantly constrains MLLMs' ability to interact effectively with the physical world.
  arXiv  Detail & Related papers  (2025-04-21T11:48:39Z)
• Brittle Minds, Fixable Activations: Understanding Belief Representations in Language Models [9.318796743761224]
  Despite growing interest in Theory of Mind (ToM) tasks for evaluating language models (LMs), little is known about how LMs internally represent mental states of self and others.<n>We present the first systematic investigation of belief representations in LMs by probing models across different scales, training regimens, and prompts.<n>Our experiments provide evidence that both model size and fine-tuning substantially improve LMs' internal representations of others' beliefs, which are structured - not mere by-products of spurious correlations - yet brittle to prompt variations.
  arXiv  Detail & Related papers  (2024-06-25T12:51:06Z)
• Calibrating Reasoning in Language Models with Internal Consistency [18.24350001344488]
  Large language models (LLMs) have demonstrated impressive capabilities in various reasoning tasks.<n>LLMs often generate text with obvious mistakes and contradictions.<n>In this work, we investigate reasoning in LLMs through the lens of internal representations.
  arXiv  Detail & Related papers  (2024-05-29T02:44:12Z)
• FANToM: A Benchmark for Stress-testing Machine Theory of Mind in Interactions [94.61530480991627]
  Theory of mind evaluations currently focus on testing models using passive narratives that inherently lack interactivity. We introduce FANToM, a new benchmark designed to stress-test ToM within information-asymmetric conversational contexts via question answering.
  arXiv  Detail & Related papers  (2023-10-24T00:24:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.